Single-sample image-fusion upsampling of fluorescence lifetime images

TL;DR

The paper introduces SiSIFUS, a novel computational method for super-resolution in fluorescence lifetime imaging microscopy that fuses low-resolution lifetime data with high-resolution intensity images using statistically informed priors.

Contribution

It presents a new data-fusion approach for FLIM super-resolution that avoids hallucination risks and can be applied to other multi-dataset image super-resolution problems.

Findings

Enhanced image resolution compared to bilinear interpolation

Bypasses out-of-distribution hallucination risks

Applicable to various image super-resolution tasks

Abstract

Fluorescence lifetime imaging microscopy (FLIM) provides detailed information about molecular interactions and biological processes. A major bottleneck for FLIM is image resolution at high acquisition speeds, due to the engineering and signal-processing limitations of time-resolved imaging technology. Here we present single-sample image-fusion upsampling (SiSIFUS), a data-fusion approach to computational FLIM super-resolution that combines measurements from a low-resolution time-resolved detector (that measures photon arrival time) and a high-resolution camera (that measures intensity only). To solve this otherwise ill-posed inverse retrieval problem, we introduce statistically informed priors that encode local and global dependencies between the two single-sample measurements. This bypasses the risk of out-of-distribution hallucination as in traditional data-driven approaches and delivers enhanced images compared for example to standard bilinear interpolation. The general approach laid out by SiSIFUS can be applied to other image super-resolution problems where two different datasets are available.